Multiple data parallelism with HPF and KeLP

Abstract

High Performance Fortran (HPF) is an effective language for implementing regular data parallel applications on distributed memory architectures, but it is not well suited to irregular, block-structured applications such as multiblock and adaptive mesh methods. A solution to this problem is to use a non-HPF SPMD program to coordinate multiple concurrent HPF tasks, each operating on a regular subgrid of an irregular data domain. To this end we have developed an interface between the C++ class library KeLP, which supports irregular, dynamic block-structured applications on distributed systems, and an HPF compiler, SHPF. This allows KeLP to handle the data layout and inter-block communications, and to invoke HPF concurrently on each block. There are a number of advantages to this approach: it combines the strengths of both KeLP and HPF; it is relatively easy to implement; and it involves no extensions to HPF or HPF compilers. This paper describes the KeLP-HPF implementation and programming model, and shows an example KeLP-HPF multiblock solver.

Correspondence should be addressed to John Merlin.